© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18648
    Prev
    Next
    INDEX
    Explanations

    young boy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fucking
    -0.09
    fuck
    -0.09
    Fuck
    -0.09
     fucked
    -0.09
     FUCK
    -0.09
    è¾Ĺ转
    -0.09
     fuck
    -0.09
     Fucked
    -0.09
    çİīçŁ³
    -0.08
    shit
    -0.08
    POSITIVE LOGITS
    å°ıä¼Ļ伴们
    0.11
    è·³åĩº
    0.10
    帮ä»ĸ
    0.10
    åıĹçģ¾
    0.09
    ç±Ģ
    0.09
    çĥŁåĽ±
    0.09
    åIJĮä¼´
    0.09
    æ£ļ
    0.09
    èµĥ
    0.09
    éĹ¹
    0.09
    Activations Density 0.103%

    No Known Activations